Skip to main content Skills Marktplatz Entdecken und erkunden Sie KI-Skills, die von der Community erstellt wurden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Prompt-Details anzeigen Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
npx skills add https://github.com/enuno/claude-command-and-control --skill lobe-chatDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
ZIP herunterladen Herunterladen... Mehr aus diesem Repository
Verwandte Berufe SOC
Basierend auf der SOC-Berufsklassifikation
name lobe-chat version 1.0.0 description LobeChat - Open-source AI agent workspace with multi-provider LLM support, plugin system, knowledge base RAG, 505+ agents, and self-hosting options via Docker/Vercel
LobeChat Skill
LobeChat is an open-source, modern AI agent workspace that provides a unified platform for conversing with multiple AI systems. It supports 20+ LLM providers (OpenAI, Claude, Gemini, Ollama), features a plugin marketplace with 40+ plugins, an agent marketplace with 505+ pre-built agents, knowledge base with RAG, and flexible deployment options.
Key Value Proposition : Deploy a private, customizable AI chat interface with multi-model support, extensible plugins, file upload/RAG capabilities, and beautiful modern UI - all self-hosted or cloud-deployed.
When to Use This Skill
Deploying LobeChat via Docker, Vercel, or other platforms
Configuring multi-provider LLM support (OpenAI, Claude, Ollama)
Creating custom agents with system prompts
Developing LobeChat plugins
Setting up knowledge base and file upload features
Configuring authentication (Clerk, NextAuth)
Troubleshooting deployment or configuration issues
When NOT to Use This Skill
For generic OpenAI/Claude API usage (use provider-specific skills)
For other chat interfaces like Open WebUI (different project)
For building AI agents from scratch (LobeChat is a ready-made solution)
For mobile app development (LobeChat is web-based with PWA)
Core Concepts
Architecture Overview
┌─────────────────────────────────────────────────────────────────┐
│ LobeChat Workspace │
│ (Next.js + TypeScript) │
└─────────────────────────────────────────────────────────────────┘
│
┌─────────────────────┼─────────────────────┐
│ │ │
▼ ▼ ▼
┌───────────────┐ ┌───────────────┐ ┌───────────────┐
│ AI Providers │ │ Agents │ │ Plugins │
├───────────────┤ ├───────────────┤ ├───────────────┤
│ • OpenAI │ │ • 505+ pre- │ │ • 40+ plugins │
│ • Claude │ │ built │ │ • Web search │
│ • Gemini │ │ • Custom │ │ • Code exec │
│ • Ollama │ │ • Marketplace │ │ • Weather │
│ • Azure │ │ • System │ │ • Custom SDK │
│ • Groq │ │ prompts │ │ │
│ • 20+ more │ │ │ │ │
└───────────────┘ └───────────────┘ └───────────────┘
│ │ │
└─────────────────────┼─────────────────────┘
│
┌─────────────────────┼─────────────────────┐
▼ ▼ ▼
┌───────────────┐ ┌───────────────┐ ┌───────────────┐
│ Knowledge Base│ │ Features │ │ Deployment │
├───────────────┤ ├───────────────┤ ├───────────────┤
│ • File upload │ │ • TTS/STT │ │ • Docker │
│ • RAG │ │ • Vision │ │ • Vercel │
│ • pgvector │ │ • Artifacts │ │ • Alibaba │
│ • Embeddings │ │ • DALL-E │ │ • Zeabur │
│ │ │ • MCP │ │ • Self-host │
└───────────────┘ └───────────────┘ └───────────────┘
Project Statistics Metric Value GitHub Stars 70.1k+ Forks 14.4k+ Contributors 313+ Total Commits 8,248+ Plugins 40+ Agents 505+ Languages TypeScript (98.5%)
Supported AI Providers Provider Models Notes OpenAI GPT-4o, GPT-4, GPT-3.5 Primary provider Anthropic Claude 3.5, Claude 3 Full model support Google Gemini Pro, Gemini Flash Vision support Azure OpenAI All OpenAI models Enterprise option Ollama Llama, Mistral, etc. Local models Groq Llama, Mixtral Fast inference Moonshot Kimi models Chinese provider 01 AI Yi models Chinese provider Together AI Open source models Many models ChatGLM GLM-4 Chinese provider Perplexity pplx-* models Search-enhanced Mistral Mistral models European provider DeepSeek DeepSeek models Coding focused
Quick Start
One-Click Vercel Deployment
Docker Deployment (Client-Side DB)
docker run -d \
--name lobe-chat \
-p 3210:3210 \
-e OPENAI_API_KEY=sk-your-key \
lobehub/lobe-chat
Docker Deployment (Server-Side DB)
docker run -d \
--name lobe-chat-db \
-p 3210:3210 \
-e DATABASE_URL=postgres://user:pass@host:5432/lobechat \
-e KEY_VAULTS_SECRET=$(openssl rand -base64 32) \
-e OPENAI_API_KEY=sk-your-key \
lobehub/lobe-chat-database
Docker Compose
version: '3.8'
services:
lobe-chat:
image: lobehub/lobe-chat-database
ports:
- "3210:3210"
environment:
- DATABASE_URL=postgres://postgres:password@db:5432/lobechat
- KEY_VAULTS_SECRET=${KEY_VAULTS_SECRET}
- OPENAI_API_KEY=${OPENAI_API_KEY}
- NEXT_AUTH_SECRET=${NEXT_AUTH_SECRET}
depends_on:
- db
db:
image: pgvector/pgvector:pg16
environment:
- POSTGRES_USER=postgres
- POSTGRES_PASSWORD=password
- POSTGRES_DB=lobechat
volumes:
- postgres_data:/var/lib/postgresql/data
volumes:
postgres_data:
export KEY_VAULTS_SECRET=$(openssl rand -base64 32)
export NEXT_AUTH_SECRET=$(openssl rand -base64 32)
export OPENAI_API_KEY=sk-your-key
docker-compose up -d
Environment Variables
Core Configuration Variable Description Required OPENAI_API_KEYOpenAI API key Yes (or other provider) ACCESS_CODEPassword protection No PROXY_URLProxy for API requests No
Database Configuration Variable Description Default NEXT_PUBLIC_SERVICE_MODEclient or serverclientDATABASE_URLPostgreSQL connection string - DATABASE_DRIVERnode or neonnodeKEY_VAULTS_SECRETEncryption key for user data Required for server mode
Provider API Keys
OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_API_KEY=...
AZURE_API_KEY=...
GROQ_API_KEY=gsk_...
OLLAMA_PROXY_URL=http://localhost:11434
Feature Configuration Variable Description Example FEATURE_FLAGSEnable/disable features +webSearch,-imageGenDEFAULT_AGENT_CONFIGDefault agent settings JSON config SYSTEM_AGENTSystem function models JSON config PLUGINS_INDEX_URLCustom plugin marketplace URL AGENTS_INDEX_URLCustom agent marketplace URL
Authentication
NEXT_AUTH_SECRET=$(openssl rand -base64 32)
NEXTAUTH_URL=https://your-domain.com
CLERK_SECRET_KEY=sk_...
NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_...
Custom Agents
Creating an Agent
Open Agent Panel → Click "+" to create new agentConfigure Settings :
Name and description
Avatar and tags
System prompt
Model selection
Temperature and parameters
Agent Configuration Structure {
"meta" : {
"name" : "Code Assistant" ,
"description" : "Expert programming assistant" ,
"avatar" : "🤖" ,
"tags" : [ "coding" , "development" ]
} ,
"config" : {
"systemRole" : "You are an expert programmer..." ,
"model" : "gpt-4o" ,
"params" : {
"temperature" : 0.3 ,
"max_tokens" : 4096
} ,
"plugins" : [ "web-search" , "code-interpreter" ] ,
"tts" : {
"enabled" : true ,
"voice" : "alloy"
}
}
}
System Prompt Best Practices # Role Definition
You are [role name], an expert in [domain].
# Core Competencies
- [Skill 1]
- [Skill 2]
- [Skill 3]
# Guidelines
1. [Guideline 1]
2. [Guideline 2]
# Response Format
- Use markdown formatting
- Include code examples when relevant
- Cite sources when possible
# Constraints
- Do not [constraint 1]
- Always [requirement 1]
Submitting to Agent Marketplace
Fork lobe-chat-agents
Create agent JSON in agents/ directory
Add metadata and system prompt
Submit pull request
Plugin Development
Plugin Architecture Plugin
├── manifest.json # Plugin definition
├── api/
│ └── endpoint.ts # Server-side handlers
└── ui/
└── index.tsx # Optional frontend UI
Quick Start with Template
git clone https://github.com/lobehub/chat-plugin-template.git
cd chat-plugin-template
npm install
npm run dev
Plugin Manifest {
"identifier" : "weather-plugin" ,
"version" : "1.0.0" ,
"api" : [
{
"url" : "http://localhost:3400/api/weather" ,
"name" : "getWeather" ,
"description" : "Get current weather for a location" ,
"parameters" : {
"type" : "object" ,
"properties" : {
"city" : {
"type" : "string" ,
"description" : "City name"
}
} ,
"required" : [ "city" ]
}
}
] ,
"ui" : {
"url" : "http://localhost:3400" ,
"height" : 400 ,
"width" : 600
} ,
"gateway" : "http://localhost:3400/api/gateway"
}
API Handler Example
import { createErrorResponse } from '@lobehub/chat-plugin-sdk' ;
export const runtime = 'edge' ;
export async function POST (req : Request try {
const { city } = await req.json ();
const response = await fetch (
`https://api.weather.com/v1/current?city=${city} `
);
const data = await response.json ();
return Response .json ({
temperature : data.temp ,
condition : data.condition ,
city : city
});
} catch (error) {
return createErrorResponse (500 , 'Failed to fetch weather' );
}
}
Frontend UI Communication
import { fetchPluginMessage } from '@lobehub/chat-plugin-sdk/client' ;
export default function PluginUI (const [message, setMessage] = useState (null );
useEffect (() => {
fetchPluginMessage ().then (setMessage);
}, []);
return (
<div >
{message && <pre > {JSON.stringify(message, null, 2)}</pre > }
</div >
Plugin SDK
npm install @lobehub/chat-plugin-sdk @lobehub/chat-plugins-gateway
import { createGateway } from '@lobehub/chat-plugins-gateway' ;
const gateway = createGateway ({
plugins : ['./manifest.json' ]
});
Publishing Plugin
Deploy to Vercel/Docker
Fork lobe-chat-plugins
Add plugin entry to index
Submit pull request
Knowledge Base & RAG
Requirements
Server-side database deployment
PostgreSQL with pgvector extension
Embedding model configured
Database Setup
CREATE EXTENSION IF NOT EXISTS vector;
Supported File Types
Documents: PDF, DOCX, TXT, MD
Images: PNG, JPG, WEBP (with vision)
Audio: MP3, WAV (with transcription)
Video: MP4 (with transcription)
Using Knowledge Base
Upload Files → Drag and drop or click uploadCreate Collection → Organize related filesAttach to Agent → Link knowledge base to agentQuery → Agent uses RAG to answer from documents
Environment Variables for RAG
EMBEDDING_MODEL=text-embedding-3-small
VECTOR_SEARCH_LIMIT=10
VECTOR_SEARCH_THRESHOLD=0.7
MCP (Model Context Protocol) LobeChat supports MCP for connecting to external tools and data sources.
Enabling MCP
MCP Server Configuration {
"mcpServers" : {
"filesystem" : {
"command" : "npx" ,
"args" : [ "-y" , "@anthropic-ai/mcp-server-filesystem" , "/path/to/files" ]
} ,
"github" : {
"command" : "npx" ,
"args" : [ "-y" , "@anthropic-ai/mcp-server-github" ] ,
"env" : {
"GITHUB_TOKEN" : "your-token"
}
}
}
}
Features
Voice Conversation (TTS/STT)
TTS_ENABLED=true
TTS_PROVIDER=openai
STT_ENABLED=true
STT_PROVIDER=openai
Image Generation
DALL_E_ENABLED=true
AI_IMAGE_DEFAULT_IMAGE_NUM=4
Artifacts Artifacts enable real-time creation and visualization of:
SVG graphics
HTML/CSS pages
React components
Interactive visualizations
Chain of Thought Visualize model reasoning steps for transparency in complex tasks.
Branching Conversations Create non-linear dialogue trees, exploring multiple conversation paths.
Deployment Options
Vercel (Recommended for Quick Start)
Fork repository
Import to Vercel
Set environment variables
Deploy
Docker
docker pull lobehub/lobe-chat
docker run -p 3210:3210 lobehub/lobe-chat
docker pull lobehub/lobe-chat-database
docker run -p 3210:3210 \
-e DATABASE_URL=... \
lobehub/lobe-chat-database
Kubernetes apiVersion: apps/v1
kind: Deployment
metadata:
name: lobe-chat
spec:
replicas: 3
selector:
matchLabels:
app: lobe-chat
template:
metadata:
labels:
app: lobe-chat
spec:
containers:
- name: lobe-chat
image: lobehub/lobe-chat-database
ports:
- containerPort: 3210
env:
- name: DATABASE_URL
valueFrom:
secretKeyRef:
name: lobe-secrets
key: database-url
Other Platforms
Zeabur : One-click deploymentSealos : Kubernetes-basedAlibaba Cloud : China-optimizedRailway : Simple hosting
Authentication
NextAuth (Docker/Self-hosted)
NEXT_AUTH_SECRET=$(openssl rand -base64 32)
NEXTAUTH_URL=https://your-domain.com
GITHUB_ID=...
GITHUB_SECRET=...
GOOGLE_ID=...
GOOGLE_SECRET=...
Clerk (Vercel) CLERK_SECRET_KEY=sk_...
NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_...
CLERK_WEBHOOK_SECRET=whsec_...
Access Code (Simple)
ACCESS_CODE=your-secret-code
Troubleshooting
API Connection Issues Error: Failed to connect to OpenAI
Verify API key is correct
Check PROXY_URL if behind firewall
Ensure network allows API access
Database Connection Failed Error: Connection refused to PostgreSQL
Verify DATABASE_URL format
Check PostgreSQL is running
Ensure pgvector extension installed
Verify network/firewall settings
Plugin Not Loading Error: Plugin manifest not found
Verify manifest URL is accessible
Check CORS settings on plugin server
Verify gateway configuration for local plugins
Knowledge Base Search Fails Error: Vector search failed
Ensure pgvector extension enabled
Check embedding model configuration
Verify file was properly indexed
Authentication Errors Error: NextAuth session invalid
Regenerate NEXT_AUTH_SECRET
Clear browser cookies
Verify NEXTAUTH_URL matches domain
Best Practices
Security
Always use ACCESS_CODE for public deploymentsGenerate strong secrets with openssl rand -base64 32Use HTTPS in productionRotate API keys regularlyEnable authentication for multi-user setups
Performance
Use server-side DB for productionConfigure caching for static assetsUse CDN via NEXT_PUBLIC_ASSET_PREFIXOptimize model selection based on task
Agents
Clear system prompts improve response qualityLower temperature (0.3-0.5) for factual tasksHigher temperature (0.7-0.9) for creative tasksUse plugins for external data access
Resources
Official Links
Marketplaces
Development
Related Projects
Version History
1.0.0 (2026-01-13): Initial skill release
Complete deployment guide (Docker, Vercel, Compose)
All environment variables documented
Custom agent creation workflow
Plugin development with SDK
Knowledge base and RAG setup
MCP integration
Authentication options (Clerk, NextAuth)
20+ AI provider configurations
Troubleshooting guide
